Nguyễn Minh Phúc
DatPySci
AI & ML interests
Reinforcement learning, NLP
Recent Activity
updated a model about 4 hours ago
DatPySci/AR-Diff published a model about 4 hours ago
DatPySci/AR-Diff updated a dataset 10 days ago
DatPySci/OpenThoughts-mixture-preprocessedOrganizations
models 99
DatPySci/AR-Diff
Updated
DatPySci/Shallow-RLVR
2B • Updated • 11
DatPySci/knowledge-context-distillation
Updated
DatPySci/pretrain-sharpen
Updated
DatPySci/RLVR-SGDM-Gap
Updated
DatPySci/LazyNTK
Updated
DatPySci/RLVR-CoTs
Updated
DatPySci/RLM
Updated
DatPySci/PreRLVR-Controlled
Updated
DatPySci/RLDI
2B • Updated • 7
datasets 73
DatPySci/OpenThoughts-mixture-preprocessed
Viewer • Updated • 114k • 56
DatPySci/OpenThoughts-114k-preprocessed
Viewer • Updated • 114k • 89
DatPySci/Self-Distillation-Qwen2.5-7B-Instruct-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 40
DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 51
DatPySci/Self-Distillation-Qwen3-8B-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 36
DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-tokenized
Viewer • Updated • 32.7k • 46
DatPySci/Self-Distillation-Qwen3-4B-Instruct-2507-medreason-tokenized
Viewer • Updated • 32.7k • 46
DatPySci/Self-Distillation-Qwen3-8B-medreason-tokenized
Viewer • Updated • 32.7k • 40
DatPySci/MedReason-tokenized
Viewer • Updated • 32.7k • 51
DatPySci/Self-Distillation-m23k-tokenized
Viewer • Updated • 23.5k • 44